agentmods.dev

agent-supagents AGENTS.md

Repository instructions for agent-supagents, a Python command-line tool that turns one Markdown instruction source into files for different coding agents. It also describes the project’s conventions, workflow, and layout.

In plain words
What is it for?
Use it when changing agent-supagents, especially when working on its CLI, agent-specific output files, plugin manifests, skills, tests, or development checks.
Why use it?
It gives contributors one place to check how the project should be developed, tested, formatted, and prepared for release. This helps keep generated agent instructions and code changes consistent.

Instructions file for CodexOpenCode

5 3mo ago A scan 773 tokens original MIT
View the source file fmind/agent-supagents
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/fmind/agent-supagents/agents-md
Clone the repo
git clone --depth 1 https://github.com/fmind/agent-supagents

Made for: Codex, OpenCode.

Per session 773 This file is loaded in full into every session.
When invoked 773 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00773 $0.00773
Opus 5 $0.00387 $0.00387
Sonnet 5 $0.00155 $0.00155
Haiku 4.5 $0.00077 $0.00077

Measured 2d ago against content hash 9888d698c098, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-supagents AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Overview

  • agent-supagents is a Python CLI (supagents) that compiles one markdown source into per-target subagent files for Claude Code, Gemini CLI, GitHub Copilot, Cursor, OpenCode, and Kilo Code.
  • The repo also ships harness manifests (.claude-plugin/, gemini-extension.json, plugin.json) and an Agent Skill under skills/use-agent-supagents/ so the same tree installs as a plugin in Claude Code, Gemini CLI, and GitHub Copilot.
  • Python ≥ 3.12. Tight dependency surface: typer, rich, ruamel.yaml, pydantic. No I/O outside the documented source/output paths.

Conventions

  • Stack & tooling. uv for env/lock; ruff (format + check) for style; ty for types; pytest (+ pytest-cov, ≥90% gate) for tests. just is the task runner — see the justfile.
  • Local checks. just lint (format + ruff + ty + uv lock --check) and just test mirror CI. Run both before opening a PR.
  • Pre-commit. The repo wires lint to pre-commit and test to pre-push (see .pre-commit-config.yaml). Don't bypass with --no-verify — fix the underlying issue.
  • Skill files. Skill bodies (skills/*/SKILL.md) load into agent context on every run; verbosity costs budget. Aim for ≤ 110 lines per SKILL.md. Use the imperative ("Read X, then write Y") and avoid second-person flavor text aimed at the human reader — that belongs in the README.

Workflow

  • For non-trivial changes, work on a feature branch and open a PR. Keep diffs focused: source-only changes shouldn't touch generated outputs from other repos.
  • When changing src/supagents/, rerun just lint and just test — the test suite covers parsing, planning, and idempotent writes.
  • When changing skills/use-agent-supagents/SKILL.md, re-read the whole file end-to-end after the edit — agents load it as a unit, so coherence matters more than line-level diffs.

Layout

  • src/supagents/ — Python package: cli.py (Typer entry points), config.py (targets, scopes), core.py (parse/plan/write), __main__.py (python -m supagents).
  • tests/ — pytest suite with fixtures under tests/fixtures/; conftest.py holds shared scaffolding.
  • skills/use-agent-supagents/SKILL.md — user-facing Agent Skill: how to author sources, run the CLI, gate CI.
  • .claude-plugin/ — Claude Code plugin manifest (plugin.json) and bundled marketplace (marketplace.json).
  • gemini-extension.json — Gemini CLI extension manifest.
  • plugin.json — GitHub Copilot plugin manifest.
  • .pre-commit-hooks.yaml — exposes the supagents-build hook so downstream repos can repo: https://github.com/fmind/agent-supagents it.
  • .github/workflows/{ci,cd}.yml — CI (lint + test on push/PR) and CD (PyPI publish on v* tags).
  • justfile — task runner: install, format, lint, test, clean, update.

Read the full file on GitHub · 33 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 33 lines · 773 tokens per session scan A 9888d698c098

Subscribe to this mod's changes

agent-supagents AGENTS.md is an instructions file published in the GitHub repository fmind/agent-supagents (5 stars, last pushed 3mo ago), licensed MIT. It adds 773 tokens to every session, about $0.0039 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

LanguagesProductivityTestingai-agentsclaude-codeclicursordeveloper-toolsgemini-cli
Related

Other instructions, from other repositories

skills CLAUDE.md

Instructions for lovstudio/skills, covering claude.md, what this is, repo layout, how users install and skills.yaml schema.

lovstudio/skills · 1,821 tokens

Dragon-Brain CLAUDE.md

Instructions for iikarus/Dragon-Brain, covering dragon brain — claude.md, the harness, audit remediation (april–may 2026, complete 2026-05-09), the lie this audit closed and the contract that matters now.

iikarus/Dragon-Brain · 6,132 tokens

cli-continues parsers.instructions.md

Instructions for yigitkonur/cli-continues, covering parser review guidelines, crash safety (critical), required exports, jsonl streaming and tool summarizer.

yigitkonur/cli-continues · 536 tokens

cli-continues security.instructions.md

Instructions for yigitkonur/cli-continues, covering security review guidelines — core utilities, command injection prevention (resume.ts), forward flag security (forward-flags.ts), handoff output safety (markdown.ts) and general.

yigitkonur/cli-continues · 419 tokens

cli-continues typescript.instructions.md

Instructions for yigitkonur/cli-continues, covering typescript review guidelines, type safety, discriminated unions, async patterns and import rules.

yigitkonur/cli-continues · 438 tokens

cli-continues ci.instructions.md

Instructions for yigitkonur/cli-continues, covering ci workflow review guidelines, security, prefer explicit permissions scoping, node.js version requirements and package manager.

yigitkonur/cli-continues · 400 tokens